© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116042
    Prev
    Next
    INDEX
    Explanations

    sequence prediction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     caracteriza
    -0.06
    characteristics
    -0.06
     najleps
    -0.06
    PLIC
    -0.06
    भारी
    -0.06
     scelta
    -0.06
     Brazil
    -0.06
     смартфон
    -0.06
     was
    -0.06
    হন
    -0.06
    POSITIVE LOGITS
     최대한
    0.07
     my
    0.06
            
    0.06
     رؤ
    0.05
     opponent
    0.05
     על
    0.05
     trés
    0.05
    毕竟
    0.05
     प्रतिबद्ध
    0.05
     преде
    0.05
    Activations Density 0.013%

    No Known Activations